Training in progress, step 188, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 800116456
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bab2ad54e5f89c4d4a2d4f1687e491181e469b1469ed095bf821be4f01a0ddca
|
| 3 |
size 800116456
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 406743412
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b2e2b40f1564925ab79b02b55b761e22ca60f3f9e63ad949a7f0484b0457173
|
| 3 |
size 406743412
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75ab5605204a9af43f26be82458c3067ada7cd350dc562ae557e7cb638991d0d
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54620d49bdfcb1656aa2450ebb6d98fa51baa9d980d3ffb410bf3ab3956d9b1f
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.295081615447998,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
-
"epoch": 2.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1089,6 +1089,272 @@
|
|
| 1089 |
"eval_samples_per_second": 11.412,
|
| 1090 |
"eval_steps_per_second": 2.907,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1112,12 +1378,12 @@
|
|
| 1112 |
"should_evaluate": false,
|
| 1113 |
"should_log": false,
|
| 1114 |
"should_save": true,
|
| 1115 |
-
"should_training_stop":
|
| 1116 |
},
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
-
"total_flos": 2.
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.295081615447998,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 2.99601593625498,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 188,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1089 |
"eval_samples_per_second": 11.412,
|
| 1090 |
"eval_steps_per_second": 2.907,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 2.406374501992032,
|
| 1095 |
+
"grad_norm": 1.7477296590805054,
|
| 1096 |
+
"learning_rate": 1.0287608105774454e-05,
|
| 1097 |
+
"loss": 0.2391,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 2.4223107569721116,
|
| 1102 |
+
"grad_norm": 1.8485106229782104,
|
| 1103 |
+
"learning_rate": 9.757637697233723e-06,
|
| 1104 |
+
"loss": 0.2419,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 2.4382470119521913,
|
| 1109 |
+
"grad_norm": 1.7354391813278198,
|
| 1110 |
+
"learning_rate": 9.240202507924412e-06,
|
| 1111 |
+
"loss": 0.1978,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 2.454183266932271,
|
| 1116 |
+
"grad_norm": 1.9352163076400757,
|
| 1117 |
+
"learning_rate": 8.735463715351139e-06,
|
| 1118 |
+
"loss": 0.2224,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.4701195219123506,
|
| 1123 |
+
"grad_norm": 2.2765555381774902,
|
| 1124 |
+
"learning_rate": 8.243578542178226e-06,
|
| 1125 |
+
"loss": 0.2753,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 2.4860557768924303,
|
| 1130 |
+
"grad_norm": 2.3106164932250977,
|
| 1131 |
+
"learning_rate": 7.764700207255903e-06,
|
| 1132 |
+
"loss": 0.4634,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 2.50199203187251,
|
| 1137 |
+
"grad_norm": 2.08597469329834,
|
| 1138 |
+
"learning_rate": 7.298977877893687e-06,
|
| 1139 |
+
"loss": 0.3889,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 2.5179282868525896,
|
| 1144 |
+
"grad_norm": 2.0033740997314453,
|
| 1145 |
+
"learning_rate": 6.8465566233957945e-06,
|
| 1146 |
+
"loss": 0.3021,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 2.5338645418326693,
|
| 1151 |
+
"grad_norm": 2.035247802734375,
|
| 1152 |
+
"learning_rate": 6.407577369873069e-06,
|
| 1153 |
+
"loss": 0.3182,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.549800796812749,
|
| 1158 |
+
"grad_norm": 1.847173810005188,
|
| 1159 |
+
"learning_rate": 5.982176856345445e-06,
|
| 1160 |
+
"loss": 0.2447,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.5657370517928286,
|
| 1165 |
+
"grad_norm": 1.7152342796325684,
|
| 1166 |
+
"learning_rate": 5.5704875921486655e-06,
|
| 1167 |
+
"loss": 0.2269,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 2.5816733067729083,
|
| 1172 |
+
"grad_norm": 1.7337571382522583,
|
| 1173 |
+
"learning_rate": 5.1726378156585816e-06,
|
| 1174 |
+
"loss": 0.2194,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 2.597609561752988,
|
| 1179 |
+
"grad_norm": 1.7184092998504639,
|
| 1180 |
+
"learning_rate": 4.788751454345763e-06,
|
| 1181 |
+
"loss": 0.2425,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 2.6135458167330676,
|
| 1186 |
+
"grad_norm": 2.0773961544036865,
|
| 1187 |
+
"learning_rate": 4.418948086172914e-06,
|
| 1188 |
+
"loss": 0.2535,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 2.6294820717131473,
|
| 1193 |
+
"grad_norm": 1.8666107654571533,
|
| 1194 |
+
"learning_rate": 4.0633429023472e-06,
|
| 1195 |
+
"loss": 0.2467,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 2.645418326693227,
|
| 1200 |
+
"grad_norm": 1.8897165060043335,
|
| 1201 |
+
"learning_rate": 3.72204667143895e-06,
|
| 1202 |
+
"loss": 0.1928,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 2.6613545816733066,
|
| 1207 |
+
"grad_norm": 1.5878872871398926,
|
| 1208 |
+
"learning_rate": 3.3951657048780227e-06,
|
| 1209 |
+
"loss": 0.2062,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 2.6772908366533863,
|
| 1214 |
+
"grad_norm": 1.7609093189239502,
|
| 1215 |
+
"learning_rate": 3.082801823838527e-06,
|
| 1216 |
+
"loss": 0.1965,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 2.6932270916334664,
|
| 1221 |
+
"grad_norm": 1.9004203081130981,
|
| 1222 |
+
"learning_rate": 2.785052327522214e-06,
|
| 1223 |
+
"loss": 0.24,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 2.709163346613546,
|
| 1228 |
+
"grad_norm": 2.4093539714813232,
|
| 1229 |
+
"learning_rate": 2.50200996285046e-06,
|
| 1230 |
+
"loss": 0.2295,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 2.7250996015936257,
|
| 1235 |
+
"grad_norm": 2.2587246894836426,
|
| 1236 |
+
"learning_rate": 2.2337628955742264e-06,
|
| 1237 |
+
"loss": 0.4213,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 2.7410358565737054,
|
| 1242 |
+
"grad_norm": 2.13430118560791,
|
| 1243 |
+
"learning_rate": 1.9803946828110375e-06,
|
| 1244 |
+
"loss": 0.4201,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 2.756972111553785,
|
| 1249 |
+
"grad_norm": 2.046278238296509,
|
| 1250 |
+
"learning_rate": 1.7419842470175195e-06,
|
| 1251 |
+
"loss": 0.3335,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 2.7729083665338647,
|
| 1256 |
+
"grad_norm": 1.6783417463302612,
|
| 1257 |
+
"learning_rate": 1.5186058514055912e-06,
|
| 1258 |
+
"loss": 0.2297,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 2.7888446215139444,
|
| 1263 |
+
"grad_norm": 1.8688119649887085,
|
| 1264 |
+
"learning_rate": 1.3103290768099797e-06,
|
| 1265 |
+
"loss": 0.2747,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 2.804780876494024,
|
| 1270 |
+
"grad_norm": 1.8578097820281982,
|
| 1271 |
+
"learning_rate": 1.1172188000142802e-06,
|
| 1272 |
+
"loss": 0.2428,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 2.8207171314741037,
|
| 1277 |
+
"grad_norm": 1.9766453504562378,
|
| 1278 |
+
"learning_rate": 9.393351735422773e-07,
|
| 1279 |
+
"loss": 0.2399,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 2.8366533864541834,
|
| 1284 |
+
"grad_norm": 2.005614995956421,
|
| 1285 |
+
"learning_rate": 7.76733606920832e-07,
|
| 1286 |
+
"loss": 0.2532,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 2.852589641434263,
|
| 1291 |
+
"grad_norm": 2.063270092010498,
|
| 1292 |
+
"learning_rate": 6.294647494202444e-07,
|
| 1293 |
+
"loss": 0.2689,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 2.8685258964143427,
|
| 1298 |
+
"grad_norm": 1.9315234422683716,
|
| 1299 |
+
"learning_rate": 4.975744742772848e-07,
|
| 1300 |
+
"loss": 0.2403,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 2.8844621513944224,
|
| 1305 |
+
"grad_norm": 1.773300051689148,
|
| 1306 |
+
"learning_rate": 3.8110386440605164e-07,
|
| 1307 |
+
"loss": 0.1952,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 2.900398406374502,
|
| 1312 |
+
"grad_norm": 2.081810474395752,
|
| 1313 |
+
"learning_rate": 2.800891996009025e-07,
|
| 1314 |
+
"loss": 0.2245,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 2.9163346613545817,
|
| 1319 |
+
"grad_norm": 1.950195550918579,
|
| 1320 |
+
"learning_rate": 1.9456194523554406e-07,
|
| 1321 |
+
"loss": 0.2327,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 2.9322709163346614,
|
| 1326 |
+
"grad_norm": 2.0852646827697754,
|
| 1327 |
+
"learning_rate": 1.245487424618108e-07,
|
| 1328 |
+
"loss": 0.211,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 2.948207171314741,
|
| 1333 |
+
"grad_norm": 1.9616092443466187,
|
| 1334 |
+
"learning_rate": 7.007139991108135e-08,
|
| 1335 |
+
"loss": 0.2025,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 2.9641434262948207,
|
| 1340 |
+
"grad_norm": 2.2779743671417236,
|
| 1341 |
+
"learning_rate": 3.1146886901090025e-08,
|
| 1342 |
+
"loss": 0.3103,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 2.9800796812749004,
|
| 1347 |
+
"grad_norm": 2.0657477378845215,
|
| 1348 |
+
"learning_rate": 7.787328150071771e-09,
|
| 1349 |
+
"loss": 0.2796,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 2.99601593625498,
|
| 1354 |
+
"grad_norm": 2.66060209274292,
|
| 1355 |
+
"learning_rate": 0.0,
|
| 1356 |
+
"loss": 0.2798,
|
| 1357 |
+
"step": 188
|
| 1358 |
}
|
| 1359 |
],
|
| 1360 |
"logging_steps": 1,
|
|
|
|
| 1378 |
"should_evaluate": false,
|
| 1379 |
"should_log": false,
|
| 1380 |
"should_save": true,
|
| 1381 |
+
"should_training_stop": true
|
| 1382 |
},
|
| 1383 |
"attributes": {}
|
| 1384 |
}
|
| 1385 |
},
|
| 1386 |
+
"total_flos": 2.9350624497342874e+17,
|
| 1387 |
"train_batch_size": 8,
|
| 1388 |
"trial_name": null,
|
| 1389 |
"trial_params": null
|